ian-xiaohei-illustrations

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its content analysis features.
  • Ingestion points: The skill reads and processes user-provided articles, URLs, and Notion pages as described in SKILL.md (Step 1).
  • Boundary markers: Missing explicit delimiters or instructions to ignore embedded commands within the ingested content when generating the prompt for the image generator.
  • Capability inventory: The skill utilizes the image_gen tool to create visual assets and writes files to the local assets/ directory (SKILL.md Step 5).
  • Sanitization: No input validation or sanitization is performed on the ingested text before it is used to define image themes and structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:10 AM
Security Audit — agent-trust-hub — ian-xiaohei-illustrations